Multi-task Driver Monitoring on AIDE (test)
78.65DER AccuracyCauPsi
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CauPsiPattern=CauPsi (ours), Multi-view Scene Backbone=MobileNetV3-S, Driver Images Backbone=MobileNetV3-S, P(M)=5.052026.04 | 78.65 | 76.84 | 92.11 | 83.25 | 82.71 | |
| MARNetPattern=3D, Multi-view Scene Backbone=MARNet, Driver Images Backbone=MARNet, Joints=3DCNN2026.04 | 76.67 | 73.61 | 93.19 | 85 | 82.3 | |
| MTS-MambaPattern=3D, Multi-view Scene Backbone=MTS-Mamba, Driver Images Backbone=MTS-Mamba, Joints=3DCNN, P(M)=5.992026.04 | 75 | 69.31 | 96.29 | 86.11 | 81.68 | |
| TimeSFormerPattern=3D, Multi-view Scene Backbone=TimeSFormer, Driver Images Backbone=TimeSFormer, Joints=ST-GCN, P(M)=158.462026.04 | 74.87 | 65.18 | 92.12 | 78.81 | 77.75 | |
| Video Swin Trans.Pattern=3D, Multi-view Scene Backbone=Video Swin Trans., Driver Images Backbone=Video Swin Trans., Joints=3DCNN, P(M)=119.802026.04 | 73.44 | 65.63 | 93.75 | 75 | 76.96 | |
| Res34+TransEPattern=2D + Timing, Multi-view Scene Backbone=Res18/34+TransE, Driver Images Backbone=Res18/34+TransE, Joints=MLP+TE2026.04 | 72.65 | 67.08 | 86.63 | 78.46 | 76.21 | |
| ShuffleNet-V1-3DPattern=3D, Multi-view Scene Backbone=ShuffleNet-V1-3D, Driver Images Backbone=ShuffleNet-V1-3D, Joints=ST-GCN, P(M)=31.492026.04 | 72.41 | 68.97 | 90.64 | 80.79 | 78.2 | |
| SlowFastPattern=3D, Multi-view Scene Backbone=SlowFast, Driver Images Backbone=SlowFast, Joints=ST-GCN2026.04 | 72.38 | 61.58 | 86.86 | 78.33 | 74.79 | |
| MobileNet-V1-3DPattern=3D, Multi-view Scene Backbone=MobileNet-V1-3D, Driver Images Backbone=MobileNet-V1-3D, Joints=ST-GCN, P(M)=54.052026.04 | 72.23 | 64.2 | 88.34 | 77.83 | 75.65 | |
| GLMDriveNetPattern=2D, Multi-view Scene Backbone=GLMDriveNet, Driver Images Backbone=GLMDriveNet, Joints=3DCNN, P(M)=78.172026.04 | 71.38 | 66.57 | 90.23 | 77.19 | 76.34 | |
| VGG16+TransEPattern=2D + Timing, Multi-view Scene Backbone=VGG13/16+TransE, Driver Images Backbone=VGG13/16+TransE, Joints=MLP+TE2026.04 | 71.12 | 67.15 | 85.13 | 78.58 | 75.5 | |
| ShuffleNet-V2-3DPattern=3D, Multi-view Scene Backbone=ShuffleNet-V2-3D, Driver Images Backbone=ShuffleNet-V2-3D, Joints=ST-GCN, P(M)=35.092026.04 | 70.94 | 64.04 | 89.33 | 78.98 | 75.82 | |
| I3DPattern=3D, Multi-view Scene Backbone=I3D, Driver Images Backbone=I3D, Joints=ST-GCN2026.04 | 70.94 | 66.17 | 87.68 | 79.81 | 76.15 | |
| PP-Res18+TransEPattern=2D + Timing, Multi-view Scene Backbone=Res18/34+TransE, Driver Images Backbone=Res18/34+TransE, Joints=MLP+TE2026.04 | 70.83 | 67.32 | 90.54 | 79.97 | 77.17 | |
| Res50+TransEPattern=2D + Timing, Multi-view Scene Backbone=Res34/50+TransE, Driver Images Backbone=Res34/50+TransE, Joints=MLP+TE2026.04 | 70.24 | 65.65 | 82.57 | 77.29 | 73.94 | |
| VGG19+TransEPattern=2D + Timing, Multi-view Scene Backbone=VGG16/19+TransE, Driver Images Backbone=VGG16/19+TransE, Joints=MLP+TE2026.04 | 69.46 | 65.48 | 85.74 | 77.91 | 74.65 | |
| 3D-Res34Pattern=3D, Multi-view Scene Backbone=3D-Res34, Driver Images Backbone=3D-Res34, Joints=3DCNN, P(M)=303.102026.04 | 69.13 | 63.05 | 87.82 | 79.31 | 74.83 | |
| VGG16Pattern=2D, Multi-view Scene Backbone=VGG16, Driver Images Backbone=VGG16, Joints=3DCNN, P(M)=127.482026.04 | 69.12 | 64.57 | 84.77 | 74.08 | 73.15 | |
| Res18Pattern=2D, Multi-view Scene Backbone=Res18, Driver Images Backbone=Res18, Joints=3DCNN, P(M)=107.772026.04 | 68.78 | 64.33 | 89.76 | 78.59 | 75.37 | |
| CMTPattern=2D, Multi-view Scene Backbone=CMT, Driver Images Backbone=CMT, Joints=3DCNN, P(M)=72.332026.04 | 68.75 | 68.75 | 93.75 | 81.38 | 78.16 | |
| MobileNet-V2-3DPattern=3D, Multi-view Scene Backbone=MobileNet-V2-3D, Driver Images Backbone=MobileNet-V2-3D, Joints=ST-GCN, P(M)=83.782026.04 | 68.47 | 61.74 | 86.54 | 78.66 | 73.85 | |
| C3DPattern=3D, Multi-view Scene Backbone=C3D, Driver Images Backbone=C3D, Joints=ST-GCN, P(M)=158.462026.04 | 63.05 | 63.95 | 85.41 | 77.01 | 72.36 |